（64）-- 爬取58同城网页信息

# 爬取58同城租房信息

from lxml import etree
import requests

base_url = 'https://bj.58.com/chuzu/?utm_source=market&spm=b-31580022738699-me-f-862.mingzhan&PGTID=0d100000-0000-17cd-3f99-94d590fc655b&ClickID=1'
response = requests.get(base_url)

html = response.text


html = etree.HTML(html)

# 找到所有房源li
li_list = html.xpath('//ul[@class="listUl"]/li')
for li in li_list:
    # 从一个房源中提取具体信息
    title = li.xpath('.//h2/a/text()')
    if title:
        title = title[0].strip()
    else:
        continue
    square = li.xpath('.//p[1]/text()')[0].replace(' ','').replace('\xa0','')
    print(title,square)from lxml import etree
import re